On the Evaluation and Comparison of Taggers: The Effect of Noise in Testing Corpora
| dc.creator | Padro, L. | |
| dc.creator | Marquez, L. | |
| dc.date | 1998-09-28 | |
| dc.date.accessioned | 2026-07-07T03:23:41Z | |
| dc.date.available | 2026-07-07T03:23:41Z | |
| dc.description | This paper addresses the issue of {\sc pos} tagger evaluation. Such evaluation is usually performed by comparing the tagger output with a reference test corpus, which is assumed to be error-free. Currently used corpora contain noise which causes the obtained performance to be a distortion of the real value. We analyze to what extent this distortion may invalidate the comparison between taggers or the measure of the improvement given by a new system. The main conclusion is that a more rigorous testing experimentation setting/designing is needed to reliably evaluate and compare tagger accuracies. | |
| dc.description | Appears in proceedings of joint COLING-ACL 1998, Montreal, Canada | |
| dc.identifier | https://arxiv.org/abs/cs/9809112 | |
| dc.identifier | http://arxiv.org/abs/cs/9809112 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/33040 | |
| dc.subject | Computation and Language | |
| dc.subject | I.2.7 | |
| dc.title | On the Evaluation and Comparison of Taggers: The Effect of Noise in Testing Corpora | |
| dc.type | text |